[UR] Support fetch adapter source individually #12907
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
kbenzie
force-pushed
the
benie/ur-per-adapter-tags
branch
from
eef1784
to
ec17d9e
Compare
kbenzie
force-pushed
the
benie/ur-per-adapter-tags
branch
from
ec17d9e
to
8eb4dae
Compare
This patch and its counterpart in oneapi-src/unified-runtime#1410 add CMake support for fetching an individual Unified Runtime adapter's source code from a different repo/tag combination using the new `fetch_adapter_source()` CMake function. Only the source is cloned, it is not added to the build directly. Instead, the path to the adapter source is passed into Unified Runtime clone described by the `UNIFIED_RUNTIME_REPO` and `UNIFIED_RUNTIME_TAG` CMake variables. This clone is the source of truth for the Unified Runtime API and drives the build of the external adapter source. Using `fetch_adapter_source()` is optional.
kbenzie
force-pushed
the
benie/ur-per-adapter-tags
branch
from
8eb4dae
to
de7976f
Compare
aarongreig
approved these changes
Mar 18, 2024
|
@intel/llvm-gatekeepers please merge |
ldrumm
pushed a commit
that referenced
this pull request
Mar 18, 2024
Implement `seq_cst` RC11/ptx6.0 memory consistency for CUDA backend. See https://dl.acm.org/doi/pdf/10.1145/3297858.3304043 and https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#memory-consistency-model for full details. Requires sm_70 or above. With this PR there is now a complete mapping between SYCL memory consistency model capabilities and the official CUDA model, fully exploiting CUDA capabilities when possible on supported arches. This makes the SYCL-CTS atomic_ref tests fully pass for sm_70 on the cuda backend. Fixes #11208 Depends on #12907 --------- Signed-off-by: JackAKirk <jack.kirk@codeplay.com>
kbenzie
pushed a commit
to kbenzie/llvm
that referenced
this pull request
Apr 15, 2024
Implement `seq_cst` RC11/ptx6.0 memory consistency for CUDA backend. See https://dl.acm.org/doi/pdf/10.1145/3297858.3304043 and https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#memory-consistency-model for full details. Requires sm_70 or above. With this PR there is now a complete mapping between SYCL memory consistency model capabilities and the official CUDA model, fully exploiting CUDA capabilities when possible on supported arches. This makes the SYCL-CTS atomic_ref tests fully pass for sm_70 on the cuda backend. Fixes intel#11208 Depends on intel#12907 --------- Signed-off-by: JackAKirk <jack.kirk@codeplay.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This patch and its counterpart in oneapi-src/unified-runtime#1410 add CMake support for fetching an individual Unified Runtime adapter's source code from a different repo/tag combination using the new
fetch_adapter_source()CMake function. Only the source is cloned, it is not added to the build directly.Instead, the path to the adapter source is passed into Unified Runtime clone described by the
UNIFIED_RUNTIME_REPOandUNIFIED_RUNTIME_TAGCMake variables. This clone is the source of truth for the Unified Runtime API and drives the build of the external adapter source.Using
fetch_adapter_source()is optional.